←back to thread

506 points imakwana | 1 comments | | HN request time: 0.21s | source
Show context
perching_aix ◴[] No.43748660[source]
> People who deactivated Facebook for the six weeks before the election reported a 0.060 standard deviation improvement in an index of happiness, depression, and anxiety, relative to controls who deactivated for just the first of those six weeks. People who deactivated Instagram for those six weeks reported a 0.041 standard deviation improvement relative to controls.

Can anyone translate? Random web search find suggests multiplying by 37 to get a percentage, which sounds very questionable, but even then these improvements seem negligible.

This doesn't really line up with my lived experience. Getting myself out of shitty platforms and community spaces improved my mental state significantly (although the damage that's been done remains).

replies(5): >>43748693 #>>43748786 #>>43748791 #>>43748803 #>>43749682 #
mmooss ◴[] No.43748791[source]
If I understand you, just read the paper for its analysis and interpretation of those numbers.

Alternatively, you'll want to grasp the meaning of "standard deviation" (you're right that you can't multiply all standard deviations by a number and get a percentage - and a percentage of what?), and then find the "index of happiness, depression, and anxiety" they use and grasp its meaning.

replies(1): >>43748848 #
perching_aix ◴[] No.43748848[source]
I'm not sure you understood me. I want to specifically avoid doing all that, to save time and effort.
replies(1): >>43754423 #
1. mmooss ◴[] No.43754423[source]
Alas, I don't know a faster way. The question asked, iiuc, demonstrates a lack of understanding of standard deviation. That's fine; none of us know everything. But without that we can't intepret the results, and also necessary is understanding what the scale represents. Thus the fastest solution seems to be reading the author's interpretation rather than trying to do it yourself.